Agent-based simulations have increasing needs in computational and memory resources when the the number of agents and interactions grows. In this paper, we are concerned with the simulation of large scale situated multi-agent systems (MAS). To be able to simulate several thousands or even a million of agents, it becomes necessary to distribute the load on a computer network. This distribution can be done in several ways and this paper presents two specific distributions: the first one is based on environment and the second one is based on agents. We illustrates the pros and cons of using both distribution types with two classical MAS applications: prey-predator and flocking behaviour models.